A reconstruction method and system for infectious internal medicine lung CT images

Abstract

The present invention relates to a reconstruction method and system for lung CT images in infectious internal medicine, wherein the method comprises: obtaining a lung CT image and a lung nuclear magnetic resonance image; detecting corresponding feature points on the lung CT image and the lung nuclear magnetic resonance image based on a Gaussian function; realizing registration of the lung CT image and the lung nuclear magnetic resonance image using a feature point matching algorithm; calculating the credibility operator of each pixel point of the lung CT image and the lung nuclear magnetic resonance image; completing the fusion of the lung CT image and the lung nuclear magnetic resonance image based on the credibility operator of each pixel point to form a reconstructed lung CT image. The present invention can integrate the information of the two images by registering and fusing the lung CT image and the nuclear magnetic resonance image, and provide more comprehensive and rich lung structure information.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a reconstruction method and system for infectious internal medicine lung CT images. Background Art

[0002] With the advancement of medical imaging technology and the expansion of its application scope, CT (Computed Tomography) imaging plays an increasingly important role in clinical diagnosis. Especially in the field of internal medicine, the application of lung CT imaging has become a routine examination item, which can provide important information about lung structure and lesions, and plays a key role in the diagnosis and treatment of lung diseases.

[0003] However, due to the complex structure of lung tissue and the presence of a large number of artifacts and noise in the images, conventional CT image reconstruction methods are difficult to accurately represent the tiny structures and lesions of the lungs to a certain extent, affecting the accuracy and reliability of the diagnostic results. Summary of the invention

[0004] To solve the above problems, an embodiment of the present invention aims to provide a method and system for reconstructing lung CT images in infectious medicine.

[0005] A reconstruction method for infectious internal medicine lung CT images, comprising:

[0006] Step 1: Obtain lung CT images and lung MRI images;

[0007] Step 2: Detect corresponding feature points on the lung CT image and lung MRI image based on the Gaussian function;

[0008] Step 3: Use feature point matching algorithm to realize registration of lung CT image and lung MRI image;

[0009] Step 4: Calculate the credibility operator of each pixel of the lung CT image and the lung MRI image;

[0010] Step 5: Based on the credibility operator of each pixel, the fusion of the lung CT image and the lung MRI image is completed to form a reconstructed lung CT image.

[0011] Preferably, the step 2: detecting corresponding feature points on the lung CT image and the lung MRI image based on a Gaussian function includes:

[0012] Step 2.1: Set the offset of each pixel in any direction;

[0013] Step 2.2: Construct a feature point screening function based on the offset of each pixel point in any direction;

[0014] Step 2.3: Use the feature point screening function to evaluate the feature change of each pixel in any direction;

[0015] Step 2.4: Pixel points whose feature variation is greater than a preset threshold are taken as corresponding feature points on the lung CT image or the lung MRI image.

[0016] Preferably, the feature point screening function is:

[0017]

[0018] Among them, E(u,v) represents the feature point screening function, ω(x,y) represents the Gaussian function, σ represents the standard deviation of the Gaussian function, I(x,y) represents the pixel value of the image at the (x,y) position, u represents the offset in the x direction, and v represents the offset in the y direction.

[0019] Preferably, the step 5: completing the fusion of the lung CT image and the lung MRI image based on the credibility operator of each pixel point to form a reconstructed lung CT image includes:

[0020] Step 5.1: Perform multi-scale decomposition on the lung CT image and the lung MRI image to obtain high-frequency image decomposition coefficients and low-frequency image decomposition coefficients;

[0021] Step 5.2: constructing a credibility operator based on the high-frequency image decomposition coefficient and the low-frequency image decomposition coefficient;

[0022] Step 5.3: Construct an information matching function based on the amount of information contained in the image;

[0023] Step 5.4: Use the information matching function and the credibility operator to complete the fusion of the lung CT image and the lung MRI image to form a reconstructed lung CT image.

[0024] Preferably, the step 5.2: constructing a credibility operator based on the high-frequency image decomposition coefficient and the low-frequency image decomposition coefficient comprises:

[0025] Step 5.2.1: Take a square neighborhood window centered at any point on the lung CT image or lung MRI image;

[0026] Step 5.2.2: performing wavelet decomposition on the square neighborhood window to obtain high-frequency image decomposition coefficients and low-frequency image decomposition coefficients of corresponding pixel points;

[0027] Step 5.2.3: Construct a credibility operator based on the high-frequency image decomposition coefficient and the low-frequency image decomposition coefficient; wherein the credibility operator is:

[0028]

[0029] Among them, Z K,L (x,y) represents the high-frequency image decomposition coefficient of the pixel point (x,y) at the kth decomposition scale, represents the mean of the low-frequency image decomposition coefficients of all pixels in the square neighborhood window, M represents the length of the square neighborhood window, and N represents the width of the square neighborhood window. Represents the low-frequency image decomposition coefficient at the point (x+r,y+c).

[0030] Preferably, the step 5.3: constructing an information matching function according to the amount of information contained in the image comprises:

[0031] Using the formula:

[0032]

[0033] Construct information matching function; where, represents the high-frequency image decomposition coefficient of the lung CT image at point (x, y), Represents the high-frequency image decomposition coefficient of the lung magnetic resonance image at point (x, y).

[0034] Preferably, the step 5.4: using the information matching function and the credibility operator to complete the fusion of the lung CT image and the lung MRI image to form a reconstructed lung CT image includes:

[0035] Step 5.4.1: Calculate the information matching value of the corresponding pixel pair using the information matching function;

[0036] Step 5.4.2: When the information matching value is greater than the set threshold, the first fusion function is used to complete the fusion of the pixels to form the fused high-frequency image decomposition coefficients; wherein the first fusion function is:

[0037]

[0038] Among them, F(x,y) represents the decomposition coefficient of the fused high-frequency image;

[0039] Step 5.4.3: When the information matching value is less than the set threshold, the second fusion function is used to complete the fusion of the pixels to form the fused high-frequency image decomposition coefficients; the second fusion function is:

[0040]

[0041] Step 5.4.4: Reconstruct the image according to the fused high-frequency image decomposition coefficients to obtain a reconstructed lung CT image.

[0042] The present invention also provides a reconstruction system for infectious internal medicine lung CT images, comprising:

[0043] A data acquisition module, used for acquiring lung CT images and lung magnetic resonance images;

[0044] A feature point calculation module is used to detect corresponding feature points on the lung CT image and the lung MRI image based on a Gaussian function;

[0045] A registration module, used for realizing registration of lung CT images and lung MRI images by using a feature point matching algorithm;

[0046] A credibility calculation module, used to calculate the credibility operator of each pixel point of the lung CT image and the lung MRI image;

[0047] The reconstruction module is used to complete the fusion of the lung CT image and the lung MRI image based on the credibility operator of each pixel point to form a reconstructed lung CT image.

[0048] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned method for reconstructing lung CT images in infectious internal medicine.

[0049] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned method for reconstructing lung CT images in infectious internal medicine are implemented.

[0050] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0051] The present invention relates to a reconstruction method for lung CT images in infectious internal medicine. Compared with the prior art, the present invention can integrate the information of the two images by registering and fusing lung CT images and nuclear magnetic resonance images, thereby providing more comprehensive and rich lung structure information.

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 A flowchart of a reconstruction method for infectious internal medicine lung CT images provided by the present invention;

[0055] Figure 2 A diagram of a reconstruction system for infectious internal medicine lung CT images provided by the present invention. DETAILED DESCRIPTION

[0056] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0057] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0058] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0059] See also Figure 1 , a reconstruction method for infectious internal medicine lung CT images, comprising:

[0060] Step 1: Obtain lung CT images and lung MRI images;

[0061] Step 2: Detect corresponding feature points on the lung CT image and lung MRI image based on the Gaussian function;

[0062] Furthermore, the step 2 comprises:

[0063] Step 2.1: Set the offset of each pixel in any direction;

[0064] Step 2.2: Construct a feature point screening function according to the offset of each pixel point in any direction; wherein the feature point screening function is:

[0065]

[0066] Among them, E(u,v) represents the feature point screening function, ω(x,y) represents the Gaussian function, σ represents the standard deviation of the Gaussian function, I(x,y) represents the pixel value of the image at the (x,y) position, u represents the offset in the x direction, and v represents the offset in the y direction.

[0067] Step 2.3: Use the feature point screening function to evaluate the feature change of each pixel in any direction;

[0068] Step 2.4: Pixel points whose feature variation is greater than a preset threshold are taken as corresponding feature points on the lung CT image or the lung MRI image.

[0069] The present invention determines whether a pixel value has a large change in the direction of a corresponding offset based on a Gaussian function, can effectively detect feature points in an image, and has high robustness against noise interference.

[0070] Step 3: Use feature point matching algorithm to realize registration of lung CT image and lung MRI image;

[0071] Step 4: Calculate the credibility operator of each pixel of the lung CT image and the lung MRI image;

[0072] Step 5: Based on the credibility operator of each pixel, the fusion of the lung CT image and the lung MRI image is completed to form a reconstructed lung CT image.

[0073] Further, step 5 includes:

[0074] Step 5.1: Perform multi-scale decomposition on the lung CT image and the lung MRI image to obtain high-frequency image decomposition coefficients and low-frequency image decomposition coefficients;

[0075] Step 5.2: constructing a credibility operator based on the high-frequency image decomposition coefficient and the low-frequency image decomposition coefficient;

[0076] Among them, step 5.2 includes:

[0077] Step 5.2.1: Take a square neighborhood window centered at any point on the lung CT image or lung MRI image;

[0078] Step 5.2.2: performing wavelet decomposition on the square neighborhood window to obtain high-frequency image decomposition coefficients and low-frequency image decomposition coefficients of corresponding pixel points;

[0079] Step 5.2.3: Construct a credibility operator based on the high-frequency image decomposition coefficient and the low-frequency image decomposition coefficient; wherein the credibility operator is:

[0080]

[0081] Among them, Z K,L (x,y) represents the high-frequency image decomposition coefficient of the pixel point (x,y) at the kth decomposition scale, represents the mean of the low-frequency image decomposition coefficients of all pixels in the square neighborhood window, M represents the length of the square neighborhood window, and N represents the width of the square neighborhood window. Represents the low-frequency image decomposition coefficient at the point (x+r,y+c).

[0082] Step 5.3: Construct an information matching function based on the amount of information contained in the image;

[0083] In the high-frequency sub-band image, when the pixel point of the image is a target point, the local discreteness contained is large and the information entropy is also large; when the pixel point of the image is a background point, the local discreteness is moderate and the information entropy is small. Since the local discreteness of the target point is larger than that of the background point, based on this, the present invention defines an energy matching function to distinguish the target point from the background point.

[0084]

[0085] in, represents the high-frequency image decomposition coefficient of the lung CT image at point (x, y), Represents the high-frequency image decomposition coefficient of the lung magnetic resonance image at point (x, y).

[0086] Step 5.4: Use the information matching function and the credibility operator to complete the fusion of the lung CT image and the lung MRI image to form a reconstructed lung CT image.

[0087] Further, the step 5.4 includes:

[0088] Step 5.4.1: Calculate the information matching value of the corresponding pixel pair using the information matching function;

[0089] Step 5.4.2: When the information matching value is greater than the set threshold, the first fusion function is used to complete the fusion of the pixels to form the fused high-frequency image decomposition coefficients; wherein the first fusion function is:

[0090]

[0091] Among them, F(x,y) represents the decomposition coefficient of the fused high-frequency image;

[0092] Step 5.4.3: When the information matching value is less than the set threshold, the second fusion function is used to complete the fusion of the pixels to form the fused high-frequency image decomposition coefficients; the second fusion function is:

[0093]

[0094] Step 5.4.4: Reconstruct the image according to the fused high-frequency image decomposition coefficients to obtain a reconstructed lung CT image.

[0095] The present invention is based on the theory of wavelet transform denoising and uses statistical methods to screen out high-frequency image decomposition coefficients corresponding to points with higher credibility, so that image fusion can be completed while removing noise points, which can increase the readability of the image.

[0096] The present invention also provides a reconstruction system for infectious internal medicine lung CT images, comprising:

[0097] A data acquisition module, used for acquiring lung CT images and lung magnetic resonance images;

[0098] A feature point calculation module is used to detect corresponding feature points on the lung CT image and the lung MRI image based on a Gaussian function;

[0099] A registration module, used for realizing registration of lung CT images and lung MRI images by using a feature point matching algorithm;

[0100] A credibility calculation module, used to calculate the credibility operator of each pixel point of the lung CT image and the lung MRI image;

[0101] The reconstruction module is used to complete the fusion of the lung CT image and the lung MRI image based on the credibility operator of each pixel point to form a reconstructed lung CT image.

[0102] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned method for reconstructing lung CT images in infectious internal medicine.

[0103] Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the method for reconstructing lung CT images for infectious internal medicine described in the above technical solution, and will not be elaborated here.

[0104] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned method for reconstructing lung CT images in infectious internal medicine are implemented.

[0105] Compared with the prior art, the beneficial effects of a computer-readable storage medium provided by the present invention are the same as the beneficial effects of a method for reconstructing lung CT images for infectious internal medicine described in the above technical solution, and will not be elaborated here.

[0106] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technical solution that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for reconstructing lung CT images in infectious medicine, characterized in that: include: Step 1: Obtain lung CT images and lung MRI images; Step 2: Detect corresponding feature points on the lung CT image and lung MRI image based on the Gaussian function; Step 3: Use feature point matching algorithm to realize registration of lung CT image and lung MRI image; Step 4: Calculate the credibility operator of each pixel of the lung CT image and the lung MRI image; Step 5: Based on the credibility operator of each pixel point, the lung CT image and the lung MRI image are fused to form a reconstructed lung CT image; The step 5: completing the fusion of the lung CT image and the lung MRI image based on the credibility operator of each pixel point to form a reconstructed lung CT image, including: Step 5.1: Perform multi-scale decomposition on the lung CT image and the lung MRI image to obtain high-frequency image decomposition coefficients and low-frequency image decomposition coefficients; Step 5.2: constructing a credibility operator based on the high-frequency image decomposition coefficient and the low-frequency image decomposition coefficient; The step 5.2: constructing a credibility operator based on the high-frequency image decomposition coefficient and the low-frequency image decomposition coefficient, comprises: Step 5.2.1: Take a square neighborhood window centered at any point on the lung CT image or lung MRI image; Step 5.2.2: performing wavelet decomposition on the square neighborhood window to obtain high-frequency image decomposition coefficients and low-frequency image decomposition coefficients of corresponding pixel points; Step 5.2.3: Construct a credibility operator based on the high-frequency image decomposition coefficient and the low-frequency image decomposition coefficient; wherein the credibility operator is: Among them, Z K,L (x,y) represents the high-frequency image decomposition coefficient of the pixel point (x,y) at the kth decomposition scale, represents the mean of the low-frequency image decomposition coefficients of all pixels in the square neighborhood window, M represents the length of the square neighborhood window, and N represents the width of the square neighborhood window. Represents the low-frequency image decomposition coefficient at the point (x+r, y+c); Step 5.3: Construct an information matching function based on the amount of information contained in the image; The step 5.3: constructing an information matching function according to the amount of information contained in the image, comprises: Using the formula: Construct information matching function; where, represents the high-frequency image decomposition coefficient of the lung CT image at point (x, y), Represents the high-frequency image decomposition coefficient of the lung magnetic resonance image at point (x, y); Step 5.4: using the information matching function and the credibility operator to complete the fusion of the lung CT image and the lung MRI image to form a reconstructed lung CT image; The step 5.4: using the information matching function and the credibility operator to complete the fusion of the lung CT image and the lung MRI image to form a reconstructed lung CT image, includes: Step 5.4.1: Calculate the information matching value of the corresponding pixel pair using the information matching function; Step 5.4.2: When the information matching value is greater than the set threshold, the first fusion function is used to complete the fusion of the pixels to form the fused high-frequency image decomposition coefficients; wherein the first fusion function is: Among them, F(x,y) represents the decomposition coefficient of the fused high-frequency image; Step 5.4.3: When the information matching value is less than the set threshold, the second fusion function is used to complete the fusion of the pixels to form the fused high-frequency image decomposition coefficients; the second fusion function is: Step 5.4.4: Reconstruct the image according to the fused high-frequency image decomposition coefficients to obtain a reconstructed lung CT image.

2. A method for reconstructing lung CT images for infectious internal medicine according to claim 1, characterized in that: The step 2: detecting corresponding feature points on the lung CT image and the lung MRI image based on the Gaussian function, includes: Step 2.1: Set the offset of each pixel in any direction; Step 2.2: Construct a feature point screening function based on the offset of each pixel point in any direction; Step 2.3: Use the feature point screening function to evaluate the feature change of each pixel in any direction; Step 2.4: Pixel points whose feature variation is greater than a preset threshold are taken as corresponding feature points on the lung CT image or the lung MRI image.

3. A method for reconstructing lung CT images for infectious internal medicine according to claim 2, characterized in that: The feature point screening function is: Among them, E(u,v) represents the feature point screening function, ω(x,y) represents the Gaussian function, σ represents the standard deviation of the Gaussian function, I(x,y) represents the pixel value of the image at the (x,y) position, u represents the offset in the x direction, and v represents the offset in the y direction.

4. A reconstruction system for infectious internal medicine lung CT images, characterized in that: include: A data acquisition module, used for acquiring lung CT images and lung magnetic resonance images; A feature point calculation module is used to detect corresponding feature points on the lung CT image and the lung MRI image based on a Gaussian function; A registration module, used for realizing registration of lung CT images and lung MRI images by using a feature point matching algorithm; A credibility calculation module, used to calculate the credibility operator of each pixel point of the lung CT image and the lung MRI image; A reconstruction module is used to complete the fusion of the lung CT image and the lung MRI image based on the credibility operator of each pixel point to form a reconstructed lung CT image; In the reconstruction module, the lung CT image and the lung MRI image are fused based on the credibility operator of each pixel point to form a reconstructed lung CT image, including: Step 5.1: Perform multi-scale decomposition on the lung CT image and the lung MRI image to obtain high-frequency image decomposition coefficients and low-frequency image decomposition coefficients; Step 5.2: constructing a credibility operator based on the high-frequency image decomposition coefficient and the low-frequency image decomposition coefficient; The step 5.2: constructing a credibility operator based on the high-frequency image decomposition coefficient and the low-frequency image decomposition coefficient, comprises: Step 5.2.1: Take a square neighborhood window centered at any point on the lung CT image or lung MRI image; Step 5.2.2: performing wavelet decomposition on the square neighborhood window to obtain high-frequency image decomposition coefficients and low-frequency image decomposition coefficients of corresponding pixel points; Step 5.2.3: Construct a credibility operator based on the high-frequency image decomposition coefficient and the low-frequency image decomposition coefficient; wherein the credibility operator is: Among them, Z K,L (x,y) represents the high-frequency image decomposition coefficient of the pixel point (x,y) at the kth decomposition scale, represents the mean of the low-frequency image decomposition coefficients of all pixels in the square neighborhood window, M represents the length of the square neighborhood window, and N represents the width of the square neighborhood window. Represents the low-frequency image decomposition coefficient at the point (x+r, y+c); Step 5.3: Construct an information matching function based on the amount of information contained in the image; The step 5.3: constructing an information matching function according to the amount of information contained in the image, comprises: Using the formula: Construct information matching function; where, represents the high-frequency image decomposition coefficient of the lung CT image at point (x, y), Represents the high-frequency image decomposition coefficient of the lung magnetic resonance image at point (x, y); Step 5.4: using the information matching function and the credibility operator to complete the fusion of the lung CT image and the lung MRI image to form a reconstructed lung CT image; The step 5.4: using the information matching function and the credibility operator to complete the fusion of the lung CT image and the lung MRI image to form a reconstructed lung CT image, includes: Step 5.4.1: Calculate the information matching value of the corresponding pixel pair using the information matching function; Step 5.4.2: When the information matching value is greater than the set threshold, the first fusion function is used to complete the fusion of the pixels to form the fused high-frequency image decomposition coefficients; wherein the first fusion function is: Among them, F(x,y) represents the decomposition coefficient of the fused high-frequency image; Step 5.4.3: When the information matching value is less than the set threshold, the second fusion function is used to complete the fusion of the pixels to form the fused high-frequency image decomposition coefficients; the second fusion function is: Step 5.4.4: Reconstruct the image according to the fused high-frequency image decomposition coefficients to obtain a reconstructed lung CT image.

5. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps of a method for reconstructing lung CT images for infectious internal medicine according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for reconstructing lung CT images for infectious internal medicine as described in any one of claims 1-3 are implemented.

Images